|
1
|
package eu.dnetlib.data.collector.plugins.schemaorg;
|
|
2
|
|
|
3
|
import org.apache.commons.logging.Log;
|
|
4
|
import org.apache.commons.logging.LogFactory;
|
|
5
|
import org.json.JSONObject;
|
|
6
|
|
|
7
|
import java.net.URL;
|
|
8
|
import java.time.LocalDate;
|
|
9
|
import java.time.format.DateTimeFormatter;
|
|
10
|
import java.util.*;
|
|
11
|
|
|
12
|
public class DatasetMappingIterator implements Iterator<String> {
|
|
13
|
private static final Log log = LogFactory.getLog(EndpointAccessIterator.class);
|
|
14
|
|
|
15
|
public static class Options {
|
|
16
|
public static class IdentifierOptions{
|
|
17
|
public List<String> mappingARK;
|
|
18
|
public List<String> mappingDOI;
|
|
19
|
public List<String> mappingHandle;
|
|
20
|
public List<String> mappingPURL;
|
|
21
|
public List<String> mappingURN;
|
|
22
|
public List<String> mappingURL;
|
|
23
|
public DatasetDocument.Identifier.IdentifierType fallbackType;
|
|
24
|
public Boolean fallbackURL;
|
|
25
|
}
|
|
26
|
|
|
27
|
public static class ContributorOptions{
|
|
28
|
public DatasetDocument.Contributor.ContributorType fallbackType;
|
|
29
|
}
|
|
30
|
|
|
31
|
public static class PublicationDateOptions{
|
|
32
|
public String format;
|
|
33
|
}
|
|
34
|
|
|
35
|
public static class CreatedDateOptions{
|
|
36
|
public String format;
|
|
37
|
}
|
|
38
|
|
|
39
|
public static class UpdatedDateOptions{
|
|
40
|
public String format;
|
|
41
|
}
|
|
42
|
|
|
43
|
private IdentifierOptions identifierOptions;
|
|
44
|
private PublicationDateOptions publicationDateOptions;
|
|
45
|
private ContributorOptions contributorOptions;
|
|
46
|
private CreatedDateOptions createdDateOptions;
|
|
47
|
private UpdatedDateOptions updatedDateOptions;
|
|
48
|
|
|
49
|
public UpdatedDateOptions getUpdatedDateOptions() {
|
|
50
|
return updatedDateOptions;
|
|
51
|
}
|
|
52
|
|
|
53
|
public void setUpdatedDateOptions(UpdatedDateOptions updatedDateOptions) {
|
|
54
|
this.updatedDateOptions = updatedDateOptions;
|
|
55
|
}
|
|
56
|
|
|
57
|
public CreatedDateOptions getCreatedDateOptions() {
|
|
58
|
return createdDateOptions;
|
|
59
|
}
|
|
60
|
|
|
61
|
public void setCreatedDateOptions(CreatedDateOptions createdDateOptions) {
|
|
62
|
this.createdDateOptions = createdDateOptions;
|
|
63
|
}
|
|
64
|
|
|
65
|
public ContributorOptions getContributorOptions() {
|
|
66
|
return contributorOptions;
|
|
67
|
}
|
|
68
|
|
|
69
|
public void setContributorOptions(ContributorOptions contributorOptions) {
|
|
70
|
this.contributorOptions = contributorOptions;
|
|
71
|
}
|
|
72
|
|
|
73
|
public PublicationDateOptions getPublicationDateOptions() {
|
|
74
|
return publicationDateOptions;
|
|
75
|
}
|
|
76
|
|
|
77
|
public void setPublicationDateOptions(PublicationDateOptions publicationDateOptions) {
|
|
78
|
this.publicationDateOptions = publicationDateOptions;
|
|
79
|
}
|
|
80
|
|
|
81
|
public IdentifierOptions getIdentifierOptions() {
|
|
82
|
return identifierOptions;
|
|
83
|
}
|
|
84
|
|
|
85
|
public void setIdentifierOptions(IdentifierOptions identifierOptions) {
|
|
86
|
this.identifierOptions = identifierOptions;
|
|
87
|
}
|
|
88
|
}
|
|
89
|
|
|
90
|
private Options options;
|
|
91
|
private EndpointAccessIterator endpointAccessIterator;
|
|
92
|
|
|
93
|
public DatasetMappingIterator(Options options, EndpointAccessIterator endpointAccessIterator) {
|
|
94
|
this.options = options;
|
|
95
|
this.endpointAccessIterator = endpointAccessIterator;
|
|
96
|
}
|
|
97
|
|
|
98
|
@Override
|
|
99
|
public boolean hasNext() {
|
|
100
|
return this.endpointAccessIterator.hasNext();
|
|
101
|
}
|
|
102
|
|
|
103
|
@Override
|
|
104
|
public String next() {
|
|
105
|
JSONObject document = this.endpointAccessIterator.next();
|
|
106
|
if (document == null) return null;
|
|
107
|
|
|
108
|
String xml = this.buildDataset(document);
|
|
109
|
|
|
110
|
return xml;
|
|
111
|
}
|
|
112
|
|
|
113
|
private String buildDataset(JSONObject document){
|
|
114
|
String xml = null;
|
|
115
|
try{
|
|
116
|
DatasetDocument dataset = new DatasetDocument();
|
|
117
|
|
|
118
|
dataset.setIdentifiers(this.extractIdentifier(document));
|
|
119
|
dataset.setCreators(this.extractCreator(document));
|
|
120
|
dataset.setTitles(this.extractTitles(document));
|
|
121
|
dataset.setAlternativeTitles(this.extractAlternateTitles(document));
|
|
122
|
dataset.setPublishers(this.extractPublisher(document));
|
|
123
|
dataset.setPublicationDates(this.extractPublicationDate(document));
|
|
124
|
dataset.setSubjects(this.extractSubjects(document));
|
|
125
|
dataset.setContributors(this.extractContributors(document));
|
|
126
|
dataset.setCreatedDates(this.extractCreatedDate(document));
|
|
127
|
dataset.setUpdatedDates(this.extractUpdatedDate(document));
|
|
128
|
dataset.setLanguages(this.extractLanguages(document));
|
|
129
|
dataset.setResourceTypes(this.extractResourceTypes(document));
|
|
130
|
dataset.setAlternateIdentifier(this.extractAlternateIdentifiers(document));
|
|
131
|
dataset.setCitations(this.extractCitations(document));
|
|
132
|
dataset.setSizes(this.extractSize(document));
|
|
133
|
dataset.setFormat(this.extractEncodingFormat(document));
|
|
134
|
dataset.setVersion(this.extractVersion(document));
|
|
135
|
dataset.setLicenses(this.extractLicense(document));
|
|
136
|
dataset.setDescriptions(this.extractDescription(document));
|
|
137
|
dataset.setDisambiguatingDescriptions(this.extractDisambiguatingDescription(document));
|
|
138
|
dataset.setGeoLocations(this.extractSpatialCoverage(document));
|
|
139
|
|
|
140
|
if((dataset.getIdentifiers() == null || dataset.getIdentifiers().size() == 0) &&
|
|
141
|
this.options.getIdentifierOptions().fallbackURL) dataset.setIdentifiers(this.extractIdentifierFallbackURL(document));
|
|
142
|
|
|
143
|
xml = dataset.toXml();
|
|
144
|
}
|
|
145
|
catch(Exception ex){
|
|
146
|
log.error("problem constructing dataset xml. returning empty", ex);
|
|
147
|
xml = null;
|
|
148
|
}
|
|
149
|
return xml;
|
|
150
|
}
|
|
151
|
|
|
152
|
private List<DatasetDocument.Identifier> extractIdentifierFallbackURL(JSONObject document){
|
|
153
|
List<String> urls = JSONLDUtils.extractString(document, "url");
|
|
154
|
|
|
155
|
ArrayList<DatasetDocument.Identifier> curated = new ArrayList<>();
|
|
156
|
for(String item : urls){
|
|
157
|
if(item == null || item.trim().length() == 0) continue;
|
|
158
|
curated.add(new DatasetDocument.Identifier(DatasetDocument.Identifier.IdentifierType.URL, item.trim()));
|
|
159
|
}
|
|
160
|
return curated;
|
|
161
|
}
|
|
162
|
|
|
163
|
private List<DatasetDocument.SpatialCoverage> extractSpatialCoverage(JSONObject document){
|
|
164
|
List<JSONLDUtils.PlaceInfo> spatials = JSONLDUtils.extractPlaces(document, "spatialCoverage");
|
|
165
|
|
|
166
|
ArrayList<DatasetDocument.SpatialCoverage> curated = new ArrayList<>();
|
|
167
|
for(JSONLDUtils.PlaceInfo item : spatials){
|
|
168
|
if((item.name == null || item.name.trim().length() == 0) &&
|
|
169
|
(item.geoCoordinates == null || item.geoCoordinates.size() == 0) &&
|
|
170
|
(item.geoShapes == null || item.geoShapes.size() == 0)) continue;
|
|
171
|
|
|
172
|
List<DatasetDocument.SpatialCoverage.Point> points = new ArrayList<>();
|
|
173
|
List<String> boxes = new ArrayList<>();
|
|
174
|
if(item.geoCoordinates!=null) {
|
|
175
|
for (JSONLDUtils.GeoCoordinatesInfo iter : item.geoCoordinates){
|
|
176
|
points.add(new DatasetDocument.SpatialCoverage.Point(iter.latitude, iter.longitude));
|
|
177
|
}
|
|
178
|
}
|
|
179
|
if(item.geoShapes!=null) {
|
|
180
|
for (JSONLDUtils.GeoShapeInfo iter : item.geoShapes){
|
|
181
|
boxes.add(iter.box);
|
|
182
|
}
|
|
183
|
}
|
|
184
|
curated.add(new DatasetDocument.SpatialCoverage(item.name, points, boxes));
|
|
185
|
}
|
|
186
|
return curated;
|
|
187
|
}
|
|
188
|
|
|
189
|
private List<String> extractDescription(JSONObject document){
|
|
190
|
List<String> descriptions = JSONLDUtils.extractString(document, "description");
|
|
191
|
|
|
192
|
ArrayList<String> curated = new ArrayList<>();
|
|
193
|
for(String item : descriptions){
|
|
194
|
if(item == null || item.trim().length() == 0) continue;
|
|
195
|
curated.add(item);
|
|
196
|
}
|
|
197
|
return curated;
|
|
198
|
}
|
|
199
|
|
|
200
|
private List<String> extractDisambiguatingDescription(JSONObject document){
|
|
201
|
List<String> descriptions = JSONLDUtils.extractString(document, "disambiguatingDescription");
|
|
202
|
|
|
203
|
ArrayList<String> curated = new ArrayList<>();
|
|
204
|
for(String item : descriptions){
|
|
205
|
if(item == null || item.trim().length() == 0) continue;
|
|
206
|
curated.add(item);
|
|
207
|
}
|
|
208
|
return curated;
|
|
209
|
}
|
|
210
|
|
|
211
|
private List<DatasetDocument.License> extractLicense(JSONObject document){
|
|
212
|
List<JSONLDUtils.LicenseInfo> licenses = JSONLDUtils.extractLicenses(document, "license");
|
|
213
|
|
|
214
|
ArrayList<DatasetDocument.License> curated = new ArrayList<>();
|
|
215
|
for(JSONLDUtils.LicenseInfo item : licenses){
|
|
216
|
if(item.url == null || item.url.trim().length() == 0) continue;
|
|
217
|
curated.add(new DatasetDocument.License(item.name, item.url));
|
|
218
|
}
|
|
219
|
return curated;
|
|
220
|
}
|
|
221
|
|
|
222
|
private List<String> extractVersion(JSONObject document){
|
|
223
|
List<String> versions = JSONLDUtils.extractString(document, "version");
|
|
224
|
|
|
225
|
ArrayList<String> curated = new ArrayList<>();
|
|
226
|
for(String item : versions){
|
|
227
|
if(item == null || item.trim().length() == 0) continue;
|
|
228
|
curated.add(item);
|
|
229
|
}
|
|
230
|
return curated;
|
|
231
|
}
|
|
232
|
|
|
233
|
private List<String> extractSize(JSONObject document) {
|
|
234
|
List<String> sizes = JSONLDUtils.extractSize(document, "distribution");
|
|
235
|
|
|
236
|
HashSet<String> curated = new HashSet<>();
|
|
237
|
for (String item : sizes) {
|
|
238
|
if (item == null || item.trim().length() == 0) continue;
|
|
239
|
curated.add(item);
|
|
240
|
}
|
|
241
|
return new ArrayList<>(curated);
|
|
242
|
}
|
|
243
|
|
|
244
|
private List<String> extractEncodingFormat(JSONObject document){
|
|
245
|
List<String> formats = JSONLDUtils.extractEncodingFormat(document, "distribution");
|
|
246
|
|
|
247
|
HashSet<String> curated = new HashSet<>();
|
|
248
|
for(String item : formats){
|
|
249
|
if(item == null || item.trim().length() == 0) continue;
|
|
250
|
curated.add(item);
|
|
251
|
}
|
|
252
|
return new ArrayList<>(curated);
|
|
253
|
}
|
|
254
|
|
|
255
|
//TODO: Handle different citation types. Currently only urls
|
|
256
|
private List<DatasetDocument.Citation> extractCitations(JSONObject document){
|
|
257
|
List<JSONLDUtils.CitationInfo> citations = JSONLDUtils.extractCitations(document, "citation");
|
|
258
|
|
|
259
|
ArrayList<DatasetDocument.Citation> curated = new ArrayList<>();
|
|
260
|
for(JSONLDUtils.CitationInfo item : citations){
|
|
261
|
if(item.url == null || item.url.trim().length() == 0) continue;
|
|
262
|
try{
|
|
263
|
new URL(item.url);
|
|
264
|
}catch (Exception ex){
|
|
265
|
continue;
|
|
266
|
}
|
|
267
|
curated.add(new DatasetDocument.Citation(item.url, DatasetDocument.Citation.CitationIdentifierType.URL));
|
|
268
|
}
|
|
269
|
return curated;
|
|
270
|
}
|
|
271
|
|
|
272
|
private List<DatasetDocument.AlternateIdentifier> extractAlternateIdentifiers(JSONObject document){
|
|
273
|
List<String> issns = JSONLDUtils.extractString(document, "issn");
|
|
274
|
List<String> urls = JSONLDUtils.extractString(document, "url");
|
|
275
|
|
|
276
|
ArrayList<DatasetDocument.AlternateIdentifier> curated = new ArrayList<>();
|
|
277
|
for(String item : issns){
|
|
278
|
if(item == null || item.trim().length() == 0) continue;
|
|
279
|
curated.add(new DatasetDocument.AlternateIdentifier(item.trim(), "ISSN"));
|
|
280
|
}
|
|
281
|
for(String item : urls){
|
|
282
|
if(item == null || item.trim().length() == 0) continue;
|
|
283
|
curated.add(new DatasetDocument.AlternateIdentifier(item.trim(), "URL"));
|
|
284
|
}
|
|
285
|
return curated;
|
|
286
|
}
|
|
287
|
|
|
288
|
private List<DatasetDocument.ResourceType> extractResourceTypes(JSONObject document){
|
|
289
|
List<DatasetDocument.ResourceType> resourceTypes = new ArrayList<>();
|
|
290
|
resourceTypes.add(new DatasetDocument.ResourceType(DatasetDocument.ResourceType.ResourceTypeGeneralType.Dataset));
|
|
291
|
return resourceTypes;
|
|
292
|
}
|
|
293
|
|
|
294
|
private List<String> extractLanguages(JSONObject document){
|
|
295
|
List<String> languages = JSONLDUtils.extractLanguage(document, "inLanguage");
|
|
296
|
|
|
297
|
ArrayList<String> curated = new ArrayList<>();
|
|
298
|
for(String item : languages){
|
|
299
|
if(item == null || item.trim().length() == 0) continue;
|
|
300
|
curated.add(item);
|
|
301
|
}
|
|
302
|
return curated;
|
|
303
|
}
|
|
304
|
|
|
305
|
private List<LocalDate> extractUpdatedDate(JSONObject document){
|
|
306
|
List<LocalDate> updatedDates = new ArrayList<>();
|
|
307
|
if(this.options.getUpdatedDateOptions() == null || this.options.getUpdatedDateOptions().format == null || this.options.getUpdatedDateOptions().format.length() == 0) return updatedDates;
|
|
308
|
|
|
309
|
DateTimeFormatter formatter = DateTimeFormatter.ofPattern(this.options.getPublicationDateOptions().format);
|
|
310
|
|
|
311
|
List<String> dates = JSONLDUtils.extractString(document, "dateModified");
|
|
312
|
for(String updatedDate : dates){
|
|
313
|
if(updatedDate == null || updatedDate.trim().length() == 0) continue;
|
|
314
|
try {
|
|
315
|
LocalDate localDate = LocalDate.parse(updatedDate, formatter);
|
|
316
|
updatedDates.add(localDate);
|
|
317
|
} catch (Exception e) {
|
|
318
|
continue;
|
|
319
|
}
|
|
320
|
}
|
|
321
|
return updatedDates;
|
|
322
|
}
|
|
323
|
|
|
324
|
private List<LocalDate> extractCreatedDate(JSONObject document){
|
|
325
|
List<LocalDate> createdDates = new ArrayList<>();
|
|
326
|
if(this.options.getCreatedDateOptions() == null || this.options.getCreatedDateOptions().format == null || this.options.getCreatedDateOptions().format.length() == 0) return createdDates;
|
|
327
|
|
|
328
|
DateTimeFormatter formatter = DateTimeFormatter.ofPattern(this.options.getCreatedDateOptions().format);
|
|
329
|
|
|
330
|
List<String> dates = JSONLDUtils.extractString(document, "dateCreated");
|
|
331
|
for(String createdDate : dates){
|
|
332
|
if(createdDate == null || createdDate.trim().length() == 0) continue;
|
|
333
|
try {
|
|
334
|
LocalDate localDate = LocalDate.parse(createdDate, formatter);
|
|
335
|
createdDates.add(localDate);
|
|
336
|
} catch (Exception e) {
|
|
337
|
continue;
|
|
338
|
}
|
|
339
|
}
|
|
340
|
return createdDates;
|
|
341
|
}
|
|
342
|
|
|
343
|
private List<DatasetDocument.Contributor> extractContributors(JSONObject document){
|
|
344
|
List<JSONLDUtils.PrincipalInfo> editors = JSONLDUtils.extractPrincipal(document, "editor");
|
|
345
|
List<JSONLDUtils.PrincipalInfo> funders = JSONLDUtils.extractPrincipal(document, "funder");
|
|
346
|
List<JSONLDUtils.PrincipalInfo> producers = JSONLDUtils.extractPrincipal(document, "producer");
|
|
347
|
List<JSONLDUtils.PrincipalInfo> sponsors = JSONLDUtils.extractPrincipal(document, "sponsor");
|
|
348
|
List<JSONLDUtils.PrincipalInfo> constributors = JSONLDUtils.extractPrincipal(document, "contributor");
|
|
349
|
|
|
350
|
ArrayList<DatasetDocument.Contributor> curated = new ArrayList<>();
|
|
351
|
for(JSONLDUtils.PrincipalInfo item : editors){
|
|
352
|
if(item.name() == null || item.name().trim().length() == 0) continue;
|
|
353
|
curated.add(new DatasetDocument.Contributor(item.name(), item.affiliationNames(), DatasetDocument.Contributor.ContributorType.Editor));
|
|
354
|
}
|
|
355
|
for(JSONLDUtils.PrincipalInfo item : funders){
|
|
356
|
if(item.name() == null || item.name().trim().length() == 0) continue;
|
|
357
|
curated.add(new DatasetDocument.Contributor(item.name(), item.affiliationNames(), DatasetDocument.Contributor.ContributorType.Funder));
|
|
358
|
}
|
|
359
|
for(JSONLDUtils.PrincipalInfo item : producers){
|
|
360
|
if(item.name() == null || item.name().trim().length() == 0) continue;
|
|
361
|
curated.add(new DatasetDocument.Contributor(item.name(), item.affiliationNames(), DatasetDocument.Contributor.ContributorType.Producer));
|
|
362
|
}
|
|
363
|
for(JSONLDUtils.PrincipalInfo item : sponsors){
|
|
364
|
if(item.name() == null || item.name().trim().length() == 0) continue;
|
|
365
|
curated.add(new DatasetDocument.Contributor(item.name(), item.affiliationNames(), DatasetDocument.Contributor.ContributorType.Sponsor));
|
|
366
|
}
|
|
367
|
for(JSONLDUtils.PrincipalInfo item : constributors){
|
|
368
|
if(item.name() == null || item.name().trim().length() == 0) continue;
|
|
369
|
DatasetDocument.Contributor.ContributorType type = DatasetDocument.Contributor.ContributorType.Other;
|
|
370
|
if(this.options.getContributorOptions()!=null && this.options.getContributorOptions().fallbackType != null) type = this.options.getContributorOptions().fallbackType;
|
|
371
|
curated.add(new DatasetDocument.Contributor(item.name(), item.affiliationNames(), type));
|
|
372
|
}
|
|
373
|
return curated;
|
|
374
|
}
|
|
375
|
|
|
376
|
private List<String> extractSubjects(JSONObject document){
|
|
377
|
List<String> subjects = JSONLDUtils.extractString(document, "keywords");
|
|
378
|
|
|
379
|
ArrayList<String> curated = new ArrayList<>();
|
|
380
|
for(String item : subjects){
|
|
381
|
if(item == null || item.trim().length() == 0) continue;
|
|
382
|
curated.add(item);
|
|
383
|
}
|
|
384
|
return curated;
|
|
385
|
}
|
|
386
|
|
|
387
|
private List<LocalDate> extractPublicationDate(JSONObject document){
|
|
388
|
List<LocalDate> publicationDates = new ArrayList<>();
|
|
389
|
if(this.options.getPublicationDateOptions() == null || this.options.getPublicationDateOptions().format == null || this.options.getPublicationDateOptions().format.length() == 0) return publicationDates;
|
|
390
|
|
|
391
|
DateTimeFormatter formatter = DateTimeFormatter.ofPattern(this.options.getPublicationDateOptions().format);
|
|
392
|
|
|
393
|
List<String> dates = JSONLDUtils.extractString(document, "datePublished");
|
|
394
|
for(String publicationDate : dates){
|
|
395
|
if(publicationDate == null || publicationDate.trim().length() == 0) continue;
|
|
396
|
try {
|
|
397
|
LocalDate localDate = LocalDate.parse(publicationDate, formatter);
|
|
398
|
publicationDates.add(localDate);
|
|
399
|
} catch (Exception e) {
|
|
400
|
continue;
|
|
401
|
}
|
|
402
|
}
|
|
403
|
return publicationDates;
|
|
404
|
}
|
|
405
|
|
|
406
|
private List<String> extractPublisher(JSONObject document){
|
|
407
|
List<JSONLDUtils.PrincipalInfo> publishers = JSONLDUtils.extractPrincipal(document, "publisher");
|
|
408
|
|
|
409
|
ArrayList<String> curated = new ArrayList<>();
|
|
410
|
for(JSONLDUtils.PrincipalInfo item : publishers){
|
|
411
|
if(item.name() == null || item.name().trim().length() == 0) continue;
|
|
412
|
curated.add(item.name());
|
|
413
|
}
|
|
414
|
return curated;
|
|
415
|
}
|
|
416
|
|
|
417
|
private List<String> extractTitles(JSONObject document){
|
|
418
|
List<String> names = JSONLDUtils.extractString(document, "name");
|
|
419
|
List<String> headlines = JSONLDUtils.extractString(document, "headline");
|
|
420
|
|
|
421
|
HashSet<String> titles = new HashSet<>();
|
|
422
|
titles.addAll(names);
|
|
423
|
titles.addAll(headlines);
|
|
424
|
return new ArrayList<>(titles);
|
|
425
|
}
|
|
426
|
|
|
427
|
private List<String> extractAlternateTitles(JSONObject document){
|
|
428
|
List<String> names = JSONLDUtils.extractString(document, "alternateName");
|
|
429
|
List<String> headlines = JSONLDUtils.extractString(document, "alternativeHeadline");
|
|
430
|
|
|
431
|
HashSet<String> titles = new HashSet<>();
|
|
432
|
titles.addAll(names);
|
|
433
|
titles.addAll(headlines);
|
|
434
|
return new ArrayList<>(titles);
|
|
435
|
}
|
|
436
|
|
|
437
|
private List<DatasetDocument.Identifier> extractIdentifier(JSONObject document){
|
|
438
|
List<DatasetDocument.Identifier> curated = new ArrayList<>();
|
|
439
|
|
|
440
|
List<JSONLDUtils.IdentifierInfo> identifiers = JSONLDUtils.extractIdentifier(document, "identifier");
|
|
441
|
|
|
442
|
for(JSONLDUtils.IdentifierInfo item : identifiers){
|
|
443
|
if(item.value == null || item.value.trim().length() == 0) continue;
|
|
444
|
if(item.type == null || item.type.trim().length() == 0) {
|
|
445
|
if (this.options.getIdentifierOptions().fallbackType == null) continue;
|
|
446
|
curated.add(new DatasetDocument.Identifier(this.options.getIdentifierOptions().fallbackType, item.value.trim()));
|
|
447
|
}
|
|
448
|
else {
|
|
449
|
DatasetDocument.Identifier.IdentifierType type = null;
|
|
450
|
if(this.options.getIdentifierOptions().mappingARK != null && this.options.getIdentifierOptions().mappingARK.contains(item.type.trim())) type = DatasetDocument.Identifier.IdentifierType.ARK;
|
|
451
|
else if(this.options.getIdentifierOptions().mappingDOI != null && this.options.getIdentifierOptions().mappingDOI.contains(item.type.trim())) type = DatasetDocument.Identifier.IdentifierType.DOI;
|
|
452
|
else if(this.options.getIdentifierOptions().mappingHandle != null && this.options.getIdentifierOptions().mappingHandle.contains(item.type.trim())) type = DatasetDocument.Identifier.IdentifierType.Handle;
|
|
453
|
else if(this.options.getIdentifierOptions().mappingPURL != null && this.options.getIdentifierOptions().mappingPURL.contains(item.type.trim())) type = DatasetDocument.Identifier.IdentifierType.PURL;
|
|
454
|
else if(this.options.getIdentifierOptions().mappingURL != null && this.options.getIdentifierOptions().mappingURL.contains(item.type.trim())) type = DatasetDocument.Identifier.IdentifierType.URL;
|
|
455
|
else if(this.options.getIdentifierOptions().mappingURN != null && this.options.getIdentifierOptions().mappingURN.contains(item.type.trim())) type = DatasetDocument.Identifier.IdentifierType.URN;
|
|
456
|
|
|
457
|
if(type == null) continue;
|
|
458
|
curated.add(new DatasetDocument.Identifier(type, item.value.trim()));
|
|
459
|
}
|
|
460
|
}
|
|
461
|
return curated;
|
|
462
|
}
|
|
463
|
|
|
464
|
private List<DatasetDocument.Creator> extractCreator(JSONObject document){
|
|
465
|
List<JSONLDUtils.PrincipalInfo> creators = JSONLDUtils.extractPrincipal(document, "creator");
|
|
466
|
List<JSONLDUtils.PrincipalInfo> authors = JSONLDUtils.extractPrincipal(document, "author");
|
|
467
|
|
|
468
|
HashSet<String> foundNames = new HashSet<>();
|
|
469
|
List<DatasetDocument.Creator> curated = new ArrayList<>();
|
|
470
|
for(JSONLDUtils.PrincipalInfo item : creators){
|
|
471
|
if(item.name() == null || item.name().trim().length() == 0) continue;
|
|
472
|
if(foundNames.contains(item.name())) continue;
|
|
473
|
foundNames.add(item.name());
|
|
474
|
curated.add(new DatasetDocument.Creator(item.name(), item.affiliationNames()));
|
|
475
|
}
|
|
476
|
for(JSONLDUtils.PrincipalInfo item : authors){
|
|
477
|
if(item.name() == null || item.name().trim().length() == 0) continue;
|
|
478
|
if(foundNames.contains(item.name())) continue;
|
|
479
|
foundNames.add(item.name());
|
|
480
|
|
|
481
|
curated.add(new DatasetDocument.Creator(item.name(), item.affiliationNames()));
|
|
482
|
}
|
|
483
|
return curated;
|
|
484
|
}
|
|
485
|
|
|
486
|
}
|